How to output several translation sentences in the OpenNMT-tf code?

[Degel37 (LakersChampionship)]

when translating each words in the input sentences, the NMT will choose the words with the highest probability. However, I want to select the words with first three highest probabilities, how can I revise the code in the opennmt-tf package so that I can get several translations for each input sentnece?

[guillaumekln (Guillaume Klein)]

Does the thread below answer your question?

How to get multiple translations for a sentence (beam search?)

After training, I would like to get multiple translations for a sentence. I am using opennmt-tf, and the config file is given at the end of this post. The command I used to get translation is: onmt-main infer --config config.yml data.yml --features_file test.txt --predictions_file translations.out In the documentation : http://opennmt.net/OpenNMT/translation/beam_search/, -beam_size and -n_best are mentioned, but I am confused where to put these two arguments in the config file. There is al…